Login in: python browser_env/auto_login.py Test AgentOccam: python eval_webarena.py --config AgentOccam/configs/AgentOccam.yml # Replace the yml config with your target one. You can use directly run bash script/run_config.sh after replacing the experiment configurations. Please check whether...
We could also study our problem in a semi-supervised setting by having an "easy" subset of examples that weak supervisors provide reliable labels for and a subset of unlabeled "hard" examples that the weak supervisor can't reliably label, a problem which we call "easy-to-hard generalization...